© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38258
    Prev
    Next
    INDEX
    Explanations

    becomes the norm

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects copular constructions that assert states or norms—especially phrases expressing “to be” or “become” linking a subject to a status or trend.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    山市
    -0.97
    มาณ
    -0.96
     específicas
    -0.90
    nski
    -0.86
     lakini
    -0.83
    atov
    -0.80
    wußt
    -0.80
    kiej
    -0.80
    러
    -0.78
    particularly
    -0.78
    POSITIVE LOGITS
     norm
    3.72
     normal
    3.36
    norm
    2.78
     normality
    2.64
    normal
    2.42
     норма
    2.41
     routine
    2.28
    Norm
    2.27
     norms
    2.27
     norma
    2.25
    Activations Density 0.062%

    No Known Activations